{"id":"https://openalex.org/W3167309429","doi":"https://doi.org/10.1109/cec45853.2021.9504770","title":"Document Clustering with Evolved Single Word Search Queries","display_name":"Document Clustering with Evolved Single Word Search Queries","publication_year":2021,"publication_date":"2021-06-28","ids":{"openalex":"https://openalex.org/W3167309429","doi":"https://doi.org/10.1109/cec45853.2021.9504770","mag":"3167309429"},"language":"en","primary_location":{"id":"doi:10.1109/cec45853.2021.9504770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec45853.2021.9504770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042068870","display_name":"Laurence Hirsch","orcid":"https://orcid.org/0000-0002-3589-9816"},"institutions":[{"id":"https://openalex.org/I71422933","display_name":"Sheffield Hallam University","ror":"https://ror.org/019wt1929","country_code":"GB","type":"education","lineage":["https://openalex.org/I71422933"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Laurence Hirsch","raw_affiliation_strings":["Sheffield Hallam University, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Sheffield Hallam University, Sheffield, UK","institution_ids":["https://openalex.org/I71422933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073115503","display_name":"Alessandro Di Nuovo","orcid":"https://orcid.org/0000-0003-2677-2650"},"institutions":[{"id":"https://openalex.org/I71422933","display_name":"Sheffield Hallam University","ror":"https://ror.org/019wt1929","country_code":"GB","type":"education","lineage":["https://openalex.org/I71422933"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alessandro Di Nuovo","raw_affiliation_strings":["Sheffield Hallam University, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Sheffield Hallam University, Sheffield, UK","institution_ids":["https://openalex.org/I71422933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082614314","display_name":"Prasanna S. Haddela","orcid":"https://orcid.org/0000-0002-6969-8772"},"institutions":[{"id":"https://openalex.org/I192365124","display_name":"Sri Lanka Institute of Information Technology","ror":"https://ror.org/00fhk4582","country_code":"LK","type":"education","lineage":["https://openalex.org/I192365124"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Prasanna Haddela","raw_affiliation_strings":["Sri Lanka Institute of Information Technology, Colombo, Sri Lanka"],"affiliations":[{"raw_affiliation_string":"Sri Lanka Institute of Information Technology, Colombo, Sri Lanka","institution_ids":["https://openalex.org/I192365124"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042068870"],"corresponding_institution_ids":["https://openalex.org/I71422933"],"apc_list":null,"apc_paid":null,"fwci":1.4193,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.85261908,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"280","last_page":"287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8438405990600586},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6675801277160645},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6618268489837646},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6457154750823975},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5915340781211853},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.524052619934082},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48632439970970154},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.43434038758277893},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.4284573495388031},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37740421295166016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2321353554725647},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06683686375617981}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8438405990600586},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6675801277160645},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6618268489837646},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6457154750823975},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5915340781211853},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.524052619934082},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48632439970970154},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.43434038758277893},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.4284573495388031},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37740421295166016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2321353554725647},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06683686375617981},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cec45853.2021.9504770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec45853.2021.9504770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:shura.shu.ac.uk:28567","is_oa":false,"landing_page_url":"http://orcid.org/0000-0002-3589-9816>,","pdf_url":null,"source":{"id":"https://openalex.org/S4306401600","display_name":"SHURA (Sheffield Hallam University Research Archive) (Sheffield Hallam University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71422933","host_organization_name":"Sheffield Hallam University","host_organization_lineage":["https://openalex.org/I71422933"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W40976687","https://openalex.org/W1493526108","https://openalex.org/W1496856754","https://openalex.org/W1584308190","https://openalex.org/W1978394996","https://openalex.org/W1994219917","https://openalex.org/W2000117996","https://openalex.org/W2027348127","https://openalex.org/W2049633694","https://openalex.org/W2058990119","https://openalex.org/W2073459066","https://openalex.org/W2092134162","https://openalex.org/W2104046064","https://openalex.org/W2112242578","https://openalex.org/W2120529703","https://openalex.org/W2149573555","https://openalex.org/W2151098288","https://openalex.org/W2564366734","https://openalex.org/W2615930912","https://openalex.org/W2753415590","https://openalex.org/W2760997042","https://openalex.org/W2769245605","https://openalex.org/W2886023301","https://openalex.org/W2904250082","https://openalex.org/W2912599891","https://openalex.org/W2953012738","https://openalex.org/W2982494647","https://openalex.org/W3010738796","https://openalex.org/W4213009331","https://openalex.org/W4250503569","https://openalex.org/W6668990524","https://openalex.org/W6743846187","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2026738364","https://openalex.org/W2096359267","https://openalex.org/W1997310773","https://openalex.org/W2901901036","https://openalex.org/W2093300859","https://openalex.org/W2124814993","https://openalex.org/W3114052401","https://openalex.org/W2163573236","https://openalex.org/W2533706070","https://openalex.org/W2105258824"],"abstract_inverted_index":{"We":[0,10,134,151],"present":[1],"a":[2,12,19,39,68,93,104,114,120],"novel,":[3],"hybrid":[4],"approach":[5],"for":[6],"clustering":[7],"text":[8,149],"databases.":[9],"use":[11],"genetic":[13],"algorithm":[14,122],"to":[15,46,54,125,130],"generate":[16],"and":[17,53,138,164],"evolve":[18],"set":[20,35],"of":[21,36,50,73,99,161,168],"single":[22],"word":[23],"search":[24,40,101,109,154],"queries":[25,43,102],"in":[26,67,78,84,87,92,103],"Apache":[27],"Lucene":[28],"format.":[29],"Clusters":[30],"are":[31,44,95],"formed":[32],"as":[33],"the":[34,48,56,71,100,108,136,158],"documents":[37,51,91,129],"matching":[38],"query.":[41],"The":[42],"optimized":[45],"maximize":[47],"number":[49,72],"returned":[52,61,96],"minimize":[55],"overlap":[57],"between":[58],"clusters":[59,74],"(documents":[60],"by":[62,97],"more":[63],"than":[64],"one":[65],"query":[66,110,155],"set).":[69],"Optionally,":[70],"can":[75],"be":[76],"specified":[77],"advance,":[79],"which":[80],"will":[81],"normally":[82],"result":[83],"an":[85,166],"improvement":[86],"performance.":[88],"Not":[89],"all":[90,127],"collection":[94],"any":[98],"set,":[105],"so":[106],"once":[107],"evolution":[111],"is":[112,117,123],"completed":[113],"second":[115],"stage":[116],"performed":[118],"whereby":[119],"KNN":[121],"applied":[124],"assign":[126],"unassigned":[128],"their":[131],"nearest":[132],"cluster.":[133],"describe":[135],"method":[137],"compare":[139],"effectiveness":[140],"with":[141],"other":[142],"well-known":[143],"existing":[144],"systems":[145],"on":[146],"8":[147],"different":[148],"datasets.":[150],"note":[152],"that":[153],"format":[156],"has":[157],"qualitative":[159],"benefits":[160],"being":[162],"interpretable":[163],"providing":[165],"explanation":[167],"cluster":[169],"construction.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
